DataMaker MCP Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
DataMaker MCP Server
The Automators DataMaker MCP (Model Context Protocol) server provides a seamless integration between DataMaker and the Model Context Protocol, enabling AI models to interact with DataMaker's powerful data generation capabilities.
π Features
Generate synthetic data using DataMaker templates
Fetch and manage DataMaker templates
Fetch and manage DataMaker connections
Push data to DataMaker connections
Large dataset handling: Automatically stores large endpoint datasets to S3 and provides summary with view links
Execute Python scripts: Dynamically execute Python code by saving scripts to S3 and running them using the DataMaker runner
Related MCP server: Snowflake Developer MCP Server
π¦ Installation
Add the following to your mcp.json file:
{
"mcpServers": {
"datamaker": {
"command": "npx",
"args": ["-y", "@automators/datamaker-mcp"],
"env": {
"DATAMAKER_API_KEY": "your-datamaker-api-key"
}
}
}
}π Prerequisites
Node.js (LTS version recommended)
pnpm package manager (v10.5.2 or later)
A DataMaker account with API access
AWS S3 bucket and credentials (for large dataset storage)
πββοΈ Usage
Large Dataset Handling
The get_endpoints tool automatically detects when a large dataset is returned (more than 10 endpoints) and:
Stores the complete dataset to your configured S3 bucket
Returns a summary showing only the first 5 endpoints
Provides a secure link to view the complete dataset (expires in 24 hours)
This prevents overwhelming responses while maintaining access to all data.
Python Script Execution
The execute_python_script tool allows you to dynamically execute Python code:
Saves the script to S3 using the
/upload-textendpointExecutes the script using the DataMaker runner via the
/execute-pythonendpointReturns the execution output once the script completes
Usage Example:
# The tool accepts Python script code and a filename
execute_python_script(
script="print('Hello from DataMaker!')",
filename="hello.py"
)This enables AI models to write and execute custom Python scripts for data processing, transformation, or any other computational tasks within the DataMaker environment.
Development Mode
Create a .env file in your project root. You can copy from env.example:
cp env.example .envThen edit .env with your actual values:
DATAMAKER_URL="https://dev.datamaker.app"
DATAMAKER_API_KEY="your-datamaker-api-key"
# S3 Configuration (optional, for large dataset storage)
S3_BUCKET="your-s3-bucket-name"
S3_REGION="us-east-1"
S3_ACCESS_KEY_ID="your-aws-access-key"
S3_SECRET_ACCESS_KEY="your-aws-secret-key"Run the server with the MCP Inspector for debugging:
pnpm devThis will start the MCP server and launch the MCP Inspector interface at http://localhost:5173.
π§ Available Scripts
pnpm build- Build the TypeScript codepnpm dev- Start the development server with MCP Inspectorpnpm changeset- Create a new changesetpnpm version- Update versions and changelogspnpm release- Build and publish the package
π’ Release Process
This project uses Changesets to manage versions, create changelogs, and publish to npm. Here's how to make a change:
Create a new branch
Make your changes
Create a changeset:
pnpm changesetFollow the prompts to describe your changes
Commit the changeset file along with your changes
Push to your branch
Create a PR on GitHub
The GitHub Actions workflow will automatically:
Create a PR with version updates and changelog
Publish to npm when the PR is merged
π€ Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
π License
MIT License - See LICENSE for details.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
This server cannot be deployed
Maintenance
Related MCP Connectors
Amazon Ads, Seller Central, Vendor Central and AMC data for AI agents. Read-only by default.
Connect your AI agent to 300+ methods and 100+ live tools
Build and manage data pipelines, add custom connectors, and chat with your data.
Use your apps from your AI: Gmail, Slack, Google Sheets, HubSpot and 2,300+ more on your accounts.
Related MCP Servers
AlicenseNot gradedqualityCmaintenanceEnables LLM agents to interact with the MOSTLY AI Platform for generating synthetic data, including training generators, managing data connectors, executing queries, and generating synthetic datasets with OAuth 2.1 authentication.2Apache 2.0- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to perform comprehensive Snowflake database operations including DDL, DML, and warehouse management. It allows users to query data, manage database objects, and configure permissions using natural language commands.MIT
- FlicenseNot gradedqualityDmaintenanceGenerates realistic, context-aware synthetic data for AI agents to populate databases, mock APIs, and create test scenarios without exposing real PII.7 npm3-
- AlicenseCqualityBmaintenanceEnables AI agents to connect to Snowflake Data Cloud and Cortex AI for executing SQL, managing warehouses, tables, pipelines, governance, and AI-powered operations through a comprehensive set of enterprise-grade tools.2451Apache 2.0